Researchers have trained a neural¹ network designed to think like the human brain to analyse millions of selfies to find what works.

 

Andrej Karpathy, a PhD student at Stanford working on Deep Learning, decided² to use a powerful, 140-million-parameter state-of-the-art Convolutional Neural Network to help work out why some selfies are more popular than other.

 

'We decided to feed it 2 million selfies from the internet, and train it to classify good selfies from bad ones,' he explained in a blog.

 

The neural network, known as ConvNet 'looked' at every one of the 2 million selfies several tens of times.

 

Each time, it tuned³ its filters in a way that best allows it to separate good selfies from bad ones.

 

'We can't very easily inspect exactly what it found (it's all jumbled⁴ up in 140 million numbers that together define the filters),' said Karpathy.

 

'A few patterns stand out for me,' he said.

 

Women were consistently ranked higher than men - to the extent there was not a single male in the top 100.

 

The position and pose of the face is quite consistent among the top images.

 

The face always occupies about 1/3 of the image, is slightly tilted⁵, and is positioned in the center and at the top.

点击收听单词发音